深度学习入门9787115485588 Chapter1

What's element-wise in numpy?

In numpy, element-wise operations refer to operations that are performed on corresponding elements of two or more arrays.

For example, if you have two numpy arrays A and B of the same shape, A + B would perform an element-wise addition, resulting in a new array where each element is the sum of the corresponding elements of A and B. Similarly, A * B would perform an element-wise multiplication, resulting in a new array where each element is the product of the corresponding elements of A and B.

Element-wise operations can also be performed between an array and a scalar value. In this case, the operation is performed on each element of the array with the scalar value.

Element-wise operations are a fundamental concept in numpy and are an efficient way to perform calculations on large arrays of data. They are also a key building block for many other operations in numpy, such as broadcasting and vectorization.

Here is an example of element-wise operations in numpy:

import numpy as np

# create two numpy arrays
a = np.array([1, 2, 3])
b = np.array([4, 5, 6])

# perform element-wise addition
c = a + b
print(c)  # Output: [5, 7, 9]

# perform element-wise multiplication
d = a * b
print(d)  # Output: [4, 10, 18]

# perform element-wise division with a scalar value
e = a / 2
print(e)  # Output: [0.5, 1.0, 1.5]

In this example, we create two numpy arrays a and b, and perform element-wise addition, multiplication, and division using operators +, *, and /. The resulting arrays c, d, and e contain the element-wise results of the corresponding operations.

What's element-wise product in numpy? explain it first, then demonstrate with python code

Element-wise product in numpy refers to a binary operation that takes two numpy arrays of the same shape and performs a pairwise multiplication between the corresponding elements of the arrays. The resulting numpy array has the same shape as the input arrays, and each element is the product of the corresponding elements from the input arrays.

For example, if you have two numpy arrays a and b of shape (m, n), where m is the number of rows and n is the number of columns, then the element-wise product of a and b will be a new array of the same shape (m, n), where the (i, j) element is the product of the (i, j) element of a and the (i, j) element of b.

Here is an example of element-wise product in numpy with Python code:

import numpy as np

# create two numpy arrays of the same shape
a = np.array([[1, 2], [3, 4]])
b = np.array([[5, 6], [7, 8]])

# perform element-wise product
c = np.multiply(a, b)

# print the result
print(c)
# Output: [[ 5 12]
#          [21 32]]

In this example, we create two numpy arrays a and b of shape (2, 2) and perform element-wise product using the multiply() function from numpy. The resulting array c has the same shape (2, 2) as the input arrays, and each element of c is the product of the corresponding elements from a and b. 

 

I have two matrix
A
1,2
3,4
B
5,6
7,8
Calculate A*B?

To calculate the product of two matrices A and B, we need to make sure that the number of columns in A is equal to the number of rows in B. In this case, both matrices A and B are of size 2x2. Therefore, we can calculate the product of A and B as follows:

import numpy as np

# define matrix A
A = np.array([[1, 2], [3, 4]])

# define matrix B
B = np.array([[5, 6], [7, 8]])

# calculate the product of A and B
C = np.dot(A, B)

# print the result
print(C)

[[19 22]
 [43 50]]

所以上面提到的element-wise不是矩阵乘法，而是单纯的对应元素进行乘法。

 

 

 

 

 

作者:Chuck Lu    GitHub